fixing traefik chart deployment!

.gitignore

@@ -1 +1,2 @@
 .env.local
+traefik-values.yaml

01_Basic_Setup/justfile

@@ -10,6 +10,7 @@ export K3S_ENABLE_REGISTRY := env("K3S_ENABLE_REGISTRY", "true")
 export SERVER_IP := env("K3S_SERVER_IP","192.168.178.45")
 export AGENT_IP := env("K3S_AGENT_IP","192.168.178.75")
 export USER := env("K3S_USER","basti")
+export LONGHORN_NAMESPACE := env("LONGHORN_NAMESPACE","longhorn-system")
 
 [private]
 default:
@@ -146,3 +147,75 @@ configure-registry:
     echo "Restarting k3s to apply registry configuration..."
     ssh "${K8S_MASTER_NODE_NAME}" "sudo systemctl restart k3s"
     echo "✓ Registry configuration applied"
+
+
+stop:
+    #!/bin/bash
+    set -euo pipefail
+    START_TIME=$(date +%s)
+    elapsed() {
+        echo "$(($(date +%s) - START_TIME))s"
+    }
+    nodenames=$(kubectl get nodes -o=jsonpath="{.items[*]['metadata.name']}")
+    for node in ${nodenames}; do
+        kubectl drain "${node}" --ignore-daemonsets --delete-emptydir-data --force --disable-eviction --grace-period=60 --timeout=180s 2>&1 || true
+        kubectl cordon "${node}"
+        echo "Node ${node} stopped."
+    done
+    echo "Drain complete. Nodes are cordoned and drained."
+
+    if helm status longhorn -n ${LONGHORN_NAMESPACE} &>/dev/null; then
+        echo "[$(elapsed)] Waiting for Longhorn volumes to be detached..."
+        TIMEOUT=90
+        ELAPSED=0
+        while [ $ELAPSED -lt $TIMEOUT ]; do
+
+            ATTACHED=$(kubectl get volumes.longhorn.io -n ${LONGHORN_NAMESPACE} -o json 2>/dev/null | \
+                jq -r '.items[] | select(.status.state == "attached") | .metadata.name' 2>/dev/null || true)
+
+            if [ -z "$ATTACHED" ]; then
+                echo "[$(elapsed)] ✓ All Longhorn volumes detached successfully"
+                break
+            fi
+
+            ATTACHED_COUNT=$(echo "$ATTACHED" | grep -c . || echo 0)
+            echo "  Still waiting for $ATTACHED_COUNT volume(s) to detach..."
+            sleep 2
+            ELAPSED=$((ELAPSED + 2))
+        done
+        if [ $ELAPSED -ge $TIMEOUT ]; then
+            echo "[$(elapsed)] ⚠ Warning: Timeout waiting for volumes to detach"
+        fi
+    fi
+
+    for node in ${nodenames}; do
+        echo "[$(elapsed)] Stopping and disabling k3s service..."
+        ssh "${node}" "sudo systemctl stop k3s 2>/dev/null || true"
+        ssh "${node}" "sudo systemctl disable k3s 2>/dev/null || true"
+    done
+
+start:
+    #!/bin/bash
+    set -euo pipefail
+    
+    is_schedulable() {
+        node_name="$1"
+        ! kubectl get node "$node_name" -o jsonpath='{.spec.unschedulable}' 2>/dev/null | grep -q "true"
+    }
+    
+    nodenames=$(kubectl get nodes -o=jsonpath="{.items[*]['metadata.name']}")
+
+
+    for node in ${nodenames}; do
+        echo "Starting k3s service on ${node}..."
+
+        if is_schedulable "$node"; then
+            echo "✓ Node $node is already schedulable"
+            exit 0
+        fi
+
+        echo "Uncordoning node $node..."
+        kubectl uncordon "$node" 2>&1 || true
+
+        echo "Wait for every node to become Ready..."
+    done

07_KubePrometheusStack/grafana-certificate.gomplate.yaml

@@ -0,0 +1,12 @@
+apiVersion: cert-manager.io/v1
+kind: Certificate
+metadata:
+  name: grafana-ingress-certificate
+  namespace: {{.Env.PROMETHEUS_NAMESPACE}}
+spec:
+  secretName: grafana-certificate-secret
+  issuerRef:
+    name: cloudflare-cluster-issuer
+    kind: ClusterIssuer
+  dnsNames:
+  - {{.Env.GRAFANA_HOST}}

07_KubePrometheusStack/justfile

@@ -1,7 +1,7 @@
 set fallback := true
 
 export PROMETHEUS_NAMESPACE := env("PROMETHEUS_NAMESPACE", "monitoring")
-#export GRAFANA_HOST := env("GRAFANA_HOST")
+export GRAFANA_HOST := env("GRAFANA_HOST", "")
 
 [private]
 default:
@@ -14,23 +14,29 @@ add-helm-repo:
 
 
 install:
-    @just add-helm-repo
+    just add-helm-repo
 
-    gomplate -f kube-stack-config-values-gomplate.yaml -o kube-stack-config-values.yaml
+    gomplate -f kube-stack-config-values.gomplate.yaml -o kube-stack-config-values.yaml
 
     @helm upgrade --cleanup-on-fail --install kube-prometheus-stack prometheus-community/kube-prometheus-stack \
         --namespace ${PROMETHEUS_NAMESPACE} \
         --create-namespace \
-        --debug \
         --wait \
         -f kube-stack-config-values.yaml
 
-    echo "kubectl port-forward svc/prometheus-grafana 8080:80 -n monitoring"
+    just KubePrometheusStack::show-ports
-    echo "kubectl port-forward svc/prometheus-kube-prometheus-prometheus 9090 -n monitoring"
+
-    echo "kubectl port-forward svc/prometheus-kube-prometheus-alertmanager 9093 -n monitoring"
+    gomplate -f ./grafana-certificate.gomplate.yaml | kubectl apply -f -
 
-    echo "Get Grafana Password:"
-    echo "kubectl get secret --namespace monitoring -l app.kubernetes.io/component=admin-secret -o jsonpath=\"{.items[0].data.admin-password}\" | base64 --decode ; echo"
 
 uninstall:
     helm uninstall kube-prometheus-stack -n ${PROMETHEUS_NAMESPACE}
+
+show-ports:
+    @echo "kubectl port-forward svc/kube-prometheus-stack-grafana 8080:80 -n ${PROMETHEUS_NAMESPACE}"
+    @echo "kubectl port-forward svc/kube-prometheus-stack-prometheus 9090 -n ${PROMETHEUS_NAMESPACE}"
+    @echo "kubectl port-forward svc/kube-prometheus-stack-alertmanager 9093 -n ${PROMETHEUS_NAMESPACE}"
+
+    @echo "Get Grafana Password:"
+    @echo "kubectl get secret --namespace monitoring -l app.kubernetes.io/component=admin-secret -o jsonpath=\"{.items[0].data.admin-user}\" | base64 --decode ; echo"
+    @echo "kubectl get secret --namespace monitoring -l app.kubernetes.io/component=admin-secret -o jsonpath=\"{.items[0].data.admin-password}\" | base64 --decode ; echo"

07_KubePrometheusStack/kube-stack-config-values-gomplate.yaml

@@ -1,13 +0,0 @@
-grafana:
-  enabled: true
-
-  ingress:
-    enabled: true
-    ingressClassName: traefik
-    annotations:
-      traefik.ingress.kubernetes.io/router.entrypoints: websecure
-    hosts:
-      - {{ .Env.GRAFANA_HOST }}
-    tls:
-      - hosts:
-          - {{ .Env.GRAFANA_HOST }}

07_KubePrometheusStack/kube-stack-config-values.gomplate.yaml

@@ -0,0 +1,23 @@
+grafana:
+  enabled: true
+
+  ingress:
+    enabled: true
+    ingressClassName: traefik
+    annotations:
+      traefik.ingress.kubernetes.io/router.entrypoints: websecure
+    hosts:
+      - {{ .Env.GRAFANA_HOST }}
+    tls:
+      - secretName: grafana-certificate-secret
+      - hosts:
+          - {{ .Env.GRAFANA_HOST }}
+    annotations:
+      traefik.ingress.kubernetes.io/router.tls: "true"
+      traefik.ingress.kubernetes.io/router.tls.certresolver: ""  # empty = use secretName, not its own resolver
+
+  grafana.ini:
+    server:
+      domain: {{ .Env.GRAFANA_HOST }}
+      root_url: https://{{ .Env.GRAFANA_HOST }}
+      serve_from_sub_path: false

07_KubePrometheusStack/kube-stack-config-values.yaml

@@ -1,2 +0,0 @@
-grafana:
-  enabled: true

Traefik/justfile

@@ -2,6 +2,7 @@ set fallback:=true
 
 export CERT_MANAGER_NAMESPACE := env("CERT_MANAGER_NAMESPACE", "cert-manager")
 export TRAEFIK_NAMESPACE := env("TRAEFIK_NAMESPACE", "traefik")
+export TRAEFIK_CHART_VERSION := env("TRAEFIK_CHART_VERSION", "v39.0.7")
 
 add-helm-repos:
     helm repo add traefik https://helm.traefik.io/traefik --force-update
@@ -15,11 +16,14 @@ install:
 
     just add-helm-repos
 
+    gomplate -f traefik-values-gomplate.yaml -o traefik-values.yaml
+
     helm upgrade traefik traefik/traefik \
      --install \
      --cleanup-on-fail \
      --namespace ${TRAEFIK_NAMESPACE} \
      --create-namespace \
+     --version ${TRAEFIK_CHART_VERSION} \
      --values traefik-values.yaml
 
     helm upgrade cert-manager jetstack/cert-manager \
@@ -60,3 +64,8 @@ status:
     echo ""
     echo "CRDs:"
     kubectl get crd | grep cert-manager.io
+
+ingressroute:
+    #!/bin/bash
+    set -euo pipefail
+    gomplate -f traefik-ingressroute-gomplate.yaml | kubectl apply -f -

Traefik/traefik-values-gomplate.yaml

@@ -1,15 +1,33 @@
+additionalArguments:
+  - "--serversTransport.insecureSkipVerify=true"
+  - "--log.level=INFO"
+
+deployment:
+  enabled: true
+  replicas: 1
+  annotations: {}
+  podAnnotations: {}
+  additionalContainers: []
+  initContainers: []
+
 ports:
   web:
+    http:
       redirections:
         entryPoint: 
           to: websecure
-        scheme: https 
+  websecure:
+    http:
+      tls:
+        enabled: true
+
 logs:
   general:
     level: DEBUG
+
 ingressRoute:
   dashboard:
     enabled: true
-    entryPoints: [web, websecure]
     matchRule: Host(`traefik-dashboard.{{ .Env.EXTERNAL_DOMAIN }}`)
-      
+    entryPoints:
+      - websecure

prometheus-stack/README.md

@@ -19,7 +19,7 @@ helm upgrade --install prometheus prometheus-community/kube-prometheus-stack \
 
 Accessing UIs via PortForwarding
 ```
-kubectl port-forward svc/prometheus-grafana 8080:80 -n monitoring
+kubectl port-forward svc/kube-prometheus-stack-grafana 8080:80 -n monitoring
 kubectl port-forward svc/prometheus-kube-prometheus-prometheus 9090 -n monitoring
 kubectl port-forward svc/prometheus-kube-prometheus-alertmanager 9093 -n monitoring
 ```